wrai.th

Mission control for your AI agents.

Stop babysitting one chat. Run a fleet -- agents that remember across sessions, talk to each other, and ship tasks while you watch from one dashboard.

Why · One-prompt setup · Install · First Project · The Dashboard · How It Works · Agents · Messaging · Memory · Tasks · MCP Tools

One binary. One SQLite file. 58 MCP tools. Zero required config.

v1.6 -- stable. Battle-tested on real multi-agent projects, API stable. Breaking changes are documented in CHANGELOG.md.

100% local by default. Optional API key for team/server deployments. No cloud, no telemetry.

💥 Why

AI agents have no persistent memory, no way to talk to each other, and no shared understanding of what they're working on. Every session starts from zero. Every agent works alone.

wrai.th is a protocol layer for agentic management. It solves the missing infrastructure between your AI agents and productive teamwork:

• Context that persists -- memory survives /clear, context resets, and session restarts. An agent that reboots picks up where it left off.
• Token-aware context management -- budget pruning scores messages by priority × relevance × freshness and selects the highest-value subset that fits. get_session_context restores full agent state in a single call.
• Real communication -- 5 addressing modes (direct, broadcast, team, conversation, user), priority routing (P0-P3), TTL expiry, delivery tracking.
• Nested tasks -- subtasks via parent_task_id, up to 3 levels deep, with roll-up. Not just a flat list -- a hierarchy that agents navigate. Optional Linear mirror for teams already on Linear.
• Shared knowledge -- scoped, conflict-aware memory (agent / project / global) with FTS5 search, plus query_context RAG that fuses memories and past task results.
• Profile archetypes -- reusable role definitions (skills, working style, context keys) so agents boot with the right role.
• Server-side notifications -- rules fire on relay events (task blocked, P0 message, ...) and fan out to delivery channels, with a test-fire endpoint.
• Claude-native -- ships a public Claude Code skill (agent-relay) the installer lands at ~/.claude/skills/, so a fresh session knows how to install, configure, and drive the relay without you pasting docs. Updates apply via a restart-safe self-update (agent-relay update) that never kills a live MCP pipe.

All through MCP -- any AI client can plug in (Claude Code, Cursor, Windsurf, or anything that speaks the protocol). Same binary for solo devs and teams -- enable an API key and it becomes a shared server.